Pinned Repositories
AgentCoder
This Repo is the official implementation of AgentCoder and AgentCoder+.
CBS
Bias Assessment and Mitigation in LLM-based Code Generation
CodeCoT
This repo provide a CoT text to code dataset, which can increase 3\% human eval performace in Llama model.
DAMO
Two Heads are Better than One: Robust Learning Meets Multi-branch Models
Effi-Code
This is the official implementation of the paper: EffiCoder: Unleashing Code Efficiency in Language Models
EffiBench
[NeurIPS 2024] EffiBench: Benchmarking the Efficiency of Automatically Generated Code
EffiLearner
[NeurIPS 2024] Self-Optimization Improves the Efficiency of Code Generation
EmpiricalStudyofTestGeneration
FeatureMapPruning
[ICLR'24] Adversarial Feature Map Pruning for Backdoor
KAT
This is the official implementation repository for the paper titled "KAT: Towards Building More Robust Models with Kolmogorov–Arnold Networks-Based Adversarial Training"
huangd1999's Repositories
huangd1999/AgentCoder
This Repo is the official implementation of AgentCoder and AgentCoder+.
huangd1999/EffiBench
[NeurIPS 2024] EffiBench: Benchmarking the Efficiency of Automatically Generated Code
huangd1999/EffiLearner
[NeurIPS 2024] Self-Optimization Improves the Efficiency of Code Generation
huangd1999/Effi-Code
This is the official implementation of the paper: EffiCoder: Unleashing Code Efficiency in Language Models
huangd1999/DAMO
Two Heads are Better than One: Robust Learning Meets Multi-branch Models
huangd1999/KAT
This is the official implementation repository for the paper titled "KAT: Towards Building More Robust Models with Kolmogorov–Arnold Networks-Based Adversarial Training"
huangd1999/CodeCoT
This repo provide a CoT text to code dataset, which can increase 3\% human eval performace in Llama model.
huangd1999/CBS
Bias Assessment and Mitigation in LLM-based Code Generation
huangd1999/EmpiricalStudyofTestGeneration
huangd1999/MindsporeThemis
Themis have been deployed in mindspore security framework, we will illustrate how to uitlize it with some scripts.
huangd1999/AgileCoder
Dynamic Collaborative Agents for Software Development
huangd1999/BackdoorBench
huangd1999/cceval
CrossCodeEval: A Diverse and Multilingual Benchmark for Cross-File Code Completion (NeurIPS 2023)
huangd1999/clash-freenode
订阅地址🚀 免费共享♻️ 定期更新✨ 科学上网🌈 请勿滥用🚫一键订阅📪
huangd1999/FeatureMapPruning
[ICLR'24] Adversarial Feature Map Pruning for Backdoor
huangd1999/FuzzingTransformerPrograms
huangd1999/BugsInPy
BugsInPy: Benchmarking Bugs in Python Projects
huangd1999/huangd1999_backup.github.io
huangd1999/ICCV23-Towards-Building-More-Robust-Models-with-Frequency-Bias
[ICCV'23] The official PyTorch implementation of our ICCV 2023 paper: 'Towards Building More Robust Models with Frequency Bias'.
huangd1999/LLMDebugger
LDB: A Large Language Model Debugger via Verifying Runtime Execution Step by Step
huangd1999/open-o1
open-o1: Using GPT-4o with CoT to Create o1-like Reasoning Chains
huangd1999/PyTER
huangd1999/SWE-agent
SWE-agent takes a GitHub issue and tries to automatically fix it, using GPT-4, or your LM of choice. It solves 12.29% of bugs in the SWE-bench evaluation set and takes just 1.5 minutes to run.